Security audit

Scale Frameworks

Security checks for vulnerabilities and agentic risk

Overview

This is a planning skill for scaling systems and organizations, with disclosed local memory and no evidence of hidden execution, network use, or credential handling.

Before installing, be aware that this skill may keep local notes about company, architecture, bottleneck, guardrail, and escalation patterns under ~/scale/. Do not let it store secrets, credentials, payment data, or sensitive identifiers, and review or delete that directory if you do not want durable scaling memory.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Hidden Instructions

High

Category: Prompt Injection
Content: integration: pending ## Scale Context   ## Bottleneck Map
Confidence: 70% confidence
Finding: Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The `never_ask` behavior explicitly directs the skill to 'stop prompting and operate silently' after a user rejects setup prompts. That creates a risk of continued background influence or action without fresh, explicit user confirmation, which undermines transparency and informed consent even if the skill is only maintaining planning state.

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The file says to confirm activation in the first exchanges, but then lists conflicting conditions: a broad trigger ('whenever the user discusses growth, bottlenecks, architecture limits, or team capacity') alongside narrower 'only when' constraints. This ambiguity can cause unintended invocation or inconsistent behavior because the scope is not clearly defined.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill instructs storing activation preferences in ~/scale/memory.md without clearly notifying the user that data will be retained. Silent persistence creates a privacy and consent risk because users may disclose operational details believing the exchange is ephemeral, while the skill saves reusable context locally for future sessions.

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The section on persisting reusable scaling intelligence establishes ongoing retention of user-derived operational context without explicit disclosure or consent. Even though it says not to store secrets, the listed categories can still include sensitive business information such as bottlenecks, interventions, guardrails, and escalation signals, which could expose internal strategy or operational weaknesses if accessed later or stored insecurely.

Static analysis

No suspicious patterns detected.